将caffe中的data和label分别写在两个layer中

ZhikangFu

于 2015-04-21 14:29:15 发布

阅读量2.5k

点赞数

CC 4.0 BY-SA版权

分类专栏： caffe

本文链接：https://blog.youkuaiyun.com/ZhikangFu/article/details/45170047

caffe 专栏收录该内容

30 篇文章

订阅专栏

本文探讨了深度学习在图像处理领域的应用，包括图像分割、语义识别、AR特效等，展示了深度学习如何提高图像处理任务的效率和准确性。

摘要生成于 C知道，由 DeepSeek-R1 满血版支持，前往体验 >

layer {
name: "data"
type: "Data"
top: "data"
include {
phase: TRAIN
}
transform_param {
mean_value: 104.00699
mean_value: 116.66877
mean_value: 122.67892
}
data_param {
source: "skin/data/traindata_lmdb"
batch_size: 1
backend: LMDB
}
}
layer {
name: "label"
type: "Data"
top: "label"
include {
phase: TRAIN
}
data_param {
source: "skin/data/trainlabel_lmdb"
batch_size: 1
backend: LMDB
}
transform_param {
# feature scaling coefficient: this maps the [0, 255] MNIST data to [0, 1]
scale: 0.00390625
}
}
layer {
name: "data"
type: "Data"
top: "data"
include {
phase: TEST
}
transform_param {
mean_value: 104.00699
mean_value: 116.66877
mean_value: 122.67892
}
data_param {
source: "skin/data/valdata_lmdb"
batch_size: 1
backend: LMDB
}
}
layer {
name: "label"
type: "Data"
top: "label"
include {
phase: TEST
}
data_param {
source: "skin/data/vallabel_lmdb"
batch_size: 1
backend: LMDB
}
transform_param {
# feature scaling coefficient: this maps the [0, 255] MNIST data to [0, 1]
scale: 0.00390625
}
}